IP Library Granted Patent US 11,238,561
Granted Patent B2
US 11,238,561 · App. 16/145,173 · Granted Feb 1, 2022

Correction of motion-based inaccuracy in point clouds

Inventors: Chen Li (Shenzhen, CN); Lu Ma (Shenzhen, CN)
Assignee: SZ DJI TECHNOLOGY CO., LTD.
G06T5/001G06K9/00201G06K9/00791G06T5/50G06T7/251G06K2209/40G06T2207/10028G06T2207/20221G06T2207/30252
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,238,561
App. No.
16/145,173
Granted
Feb 1, 2022
Kind
B2
Abstract

Correcting motion-based inaccuracy in point cloud data generated by one or more sensors carried by a scanning platform, and associated systems and methods are disclosed herein. A representative method includes associating a motion model with a target object of the point cloud, estimating adjusting factors based on the motion model, and adjusting scanning points in the point cloud using the adjusting factors.

Claims (41)

1. A computer-implemented method for adjusting point clouds generated using at least one scanner carried by a scanning platform, the method comprising:

obtaining base point cloud information comprising a plurality of scanning points that are produced by the scanner, wherein each of at least a subset of the scanning points indicates a position of at least a portion of a target object and wherein at least two scanning points of the plurality of scanning points are produced at different times;

assessing the base point cloud information to determine estimated motion model factors;

relocating one or more scanning points of the plurality of scanning points based, at least in part, on an estimated motion of the target object in accordance with a motion model associated with the target object and in accordance with the determined estimated motion model factors;

generating an adjusted point cloud based, at least in part, on the relocating of the one or more scanning points;

determining an error distance of the adjusted point cloud;

comparing the error distance to a threshold; and

determining a maximum time period for generating the adjusted point cloud based on the comparison.

2. The method of claim 1 , further comprising determining the estimated motion of the target object based, at least in part, on a volume defined by the plurality of scanning points.

3. The method of claim 2 , wherein the volume defined in accordance with the plurality of scanning points includes a minimized quantity of volume pixels occupied by the scanning points at a target timepoint, in accordance with the motion model associated with the target object.

4. The method of claim 2 , wherein the volume defined in accordance with the plurality of scanning points includes a minimized volume enclosed by the scanning points at a target timepoint, in accordance with the motion model associated with the target object.

5. The method of claim 1 , wherein the plurality of scanning points is produced within a period of time.

6. The method of claim 5 , wherein a relative distance between the target object and the scanning platform changes during the period of time.

7. The method of claim 5 , wherein the adjusted point cloud represents at least one of a location, orientation, or shape of the target object at the end of the period of time.

8. The method of claim 1 , wherein the estimated motion of the target object includes at least one of a translational motion or a rotational motion.

9. The method of claim 1 , further comprising locating the target object based, at least in part, on the adjusted point cloud.

10. A non-transitory computer-readable medium storing computer-executable instructions that, when executed, cause one or more processors associated with a scanning platform to perform actions, the actions comprising:

obtaining base point cloud information comprising a plurality of scanning points that are produced by at least one scanner, wherein each of at least a subset of the scanning points indicates a position of at least a portion of a target object and wherein at least two scanning points of the plurality of scanning points are produced at different times;

assessing the base point cloud information to determine estimated motion model factors;

relocating one or more scanning points of the plurality of scanning points based, at least in part, on an estimated motion of the target object in accordance with a motion model associated with the target object and in accordance with the determined estimated motion model factors;

generating an adjusted point cloud based, at least in part, on the relocating of the one or more scanning points;

determining an error distance of the adjusted point cloud;

comparing the error distance to a threshold; and

determining a maximum time period for generating the adjusted point cloud based on the comparison.

11. The computer-readable medium of claim 10 , wherein the positions indicated by at least two of the scanning points correspond to different portions of the target object.

12. The computer-readable medium of claim 10 , wherein the scanning points are represented within a three-dimensional reference system associated with the at least one scanner or the scanning platform.

13. The computer-readable medium of claim 10 , wherein the actions further comprise estimating a motion of the target object based, at least in part, on the motion model that includes at least one of a translational motion component or a rotational motion component.

14. The computer-readable medium of claim 13 , wherein the translational motion component includes at least one of a constant translational speed factor or a variable translational speed factor.

15. The computer-readable medium of claim 13 , wherein the rotational motion component includes at least one of a constant rotational speed factor or a variable rotational speed factor.

16. A vehicle including a controller programmed to at least partially control one or more motions of the vehicle, wherein the programmed controller includes one or more processors configured to:

obtain base point cloud information comprising a plurality of scanning points that are produced by at least one scanner, wherein each of at least a subset of the scanning points indicates a position of at least a portion of a target object and wherein at least two scanning points of the plurality of scanning points are produced at different times;

assess the base point cloud information to determine estimated motion model factors;

relocate one or more scanning points of the plurality of scanning points based, at least in part, on an estimated motion of the target object in accordance with a motion model associated with the target object and in accordance with the determined estimated motion model factors;

generate an adjusted point cloud based, at least in part, on the relocating of the one or more scanning points;

determine an error distance of the adjusted point cloud;

compare the error distance to a threshold; and

determine a maximum time period for generating the adjusted point cloud based on the comparison.

17. The vehicle of claim 16 , wherein the one or more processors are further configured to determine the estimated motion of the target object based, at least in part, on a volume defined by the plurality of scanning points.

18. The vehicle of claim 16 , wherein the plurality of scanning points is produced within a period of time.

19. The vehicle of claim 18 , wherein the adjusted point cloud represents at least one of a location, orientation, or shape of the target object at the end of the period of time.

20. The vehicle of claim 16 , wherein the vehicle includes at least one of an unmanned aerial vehicle (UAV), a manned aircraft, an autonomous car, a self-balancing vehicle, a robot, a smart wearable device, a virtual reality (VR) head-mounted display, or an augmented reality (AR) head-mounted display.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 17, 2024
From: SZ DJI TECHNOLOGY CO., LTD.
To: SHENZHEN ZHUOYU TECHNOLOGY CO., LTD.
Reel/Frame 067452/0494 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 14, 2019
From: LI, CHEN; MA, LU
To: SZ DJI TECHNOLOGY CO., LTD.,
Reel/Frame 048337/0018 →
Continuity (3)
Continuation 15729533 · Oct 10, 2017
Continuation PCTCN2017095300 · Jul 31, 2017
Related Publication 20190043170A1 · Feb 7, 2019